© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 5589
    Prev
    Next
    INDEX
    Explanations

    references to medical testing and diseases, particularly Ebola and Zika

    oai_token-act-pair · gpt-3.5-turbo

    references to health-related issues and diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srfAttach
    -1.00
     Garage
    -0.93
     Architects
    -0.87
    Asset
    -0.87
    Tokens
    -0.85
    sbm
    -0.81
    ensional
    -0.78
     guitars
    -0.78
    UGC
    -0.78
    iture
    -0.77
    POSITIVE LOGITS
     infected
    1.80
     Ebola
    1.74
     infection
    1.74
     vaccine
    1.70
     virus
    1.70
     vaccination
    1.69
     infections
    1.63
     vaccinated
    1.61
     measles
    1.60
     Zika
    1.58
    Activations Density 0.394%

    No Known Activations